## [1] "Sample size = 346"
## [1] "Loci = 244"
## [1] "1 to 130 alleles per locus per sample"
## [1] "Overall % dimers (already multiplied x100)"
## [1] 0.5306955
## [1] "Max number of reads in a locus"
## [1] 344
## [1] "List of loci with >100 reads (summed over all negative controls)"
## # A tibble: 25 × 5
## locus reads pool Gene Reason_to_include
## <chr> <int> <chr> <chr> <chr>
## 1 Pf3D7_13_v3-2814583-2814832-2 344 2 EBL-1 HRP3 deletion
## 2 Pf3D7_11_v3-1902041-1902278-2 290 2 MAEBL ch11
## 3 Pf3D7_13_v3-1726174-1726408-2 269 2 k13 <NA>
## 4 Pf3D7_12_v3-2092654-2092884-2 249 2 coronin 100
## 5 Pf3D7_13_v3-1725124-1725365-2 195 2 k13 613
## 6 Pf3D7_13_v3-1725887-1726123-2 176 2 k13 <NA>
## 7 Pf3D7_13_v3-2770591-2770863-2 170 2 PF3D7_1369500 HRP3 deletion
## 8 Pf3D7_11_v3-1950431-1950680-2 169 2 Pf332 ch11
## 9 Pf3D7_14_v3-294503-294768-2 160 2 pm2 cnv
## 10 Pf3D7_03_v3-221295-221532-2 159 2 csp C-terminal
## # ℹ 15 more rows
## [1] "Mean of total locus = 214, Mean prop. of monoclonal loci = 0.85, Mean prop. of polyclonal loci = 0.15"
## [1] "Mean of total locus = 187.52, Mean prop. of monoclonal loci = 0.93, Mean prop. of polyclonal loci = 0.07"
##
## 1A 1AB 1B 1B2 2
## 165 5 75 2 29
## [1] "Pf3D7_01_v3-162867-163115-1A" "Pf3D7_01_v3-194742-194973-1B"
## [3] "Pf3D7_01_v3-455794-456054-1A" "Pf3D7_01_v3-535965-536239-1A"
## [5] "Pf3D7_02_v3-291770-292017-1A" "Pf3D7_02_v3-320652-320949-2"
## [7] "Pf3D7_02_v3-628941-629172-1A" "Pf3D7_03_v3-221295-221532-2"
## [9] "Pf3D7_03_v3-221463-221712-1B" "Pf3D7_03_v3-240957-241256-2"
## [11] "Pf3D7_03_v3-891553-891827-1A" "Pf3D7_04_v3-1083299-1083563-2"
## [13] "Pf3D7_04_v3-1113397-1113639-1A" "Pf3D7_04_v3-141741-141990-1A"
## [15] "Pf3D7_04_v3-648065-648332-1A" "Pf3D7_05_v3-1322099-1322341-1A"
## [17] "Pf3D7_05_v3-369676-369949-1A" "Pf3D7_05_v3-615379-615678-2"
## [19] "Pf3D7_05_v3-641131-641404-1A" "Pf3D7_06_v3-1115900-1116168-1A"
## [21] "Pf3D7_06_v3-1128558-1128797-1A" "Pf3D7_06_v3-1135605-1135855-1A"
## [23] "Pf3D7_06_v3-1136091-1136364-1A" "Pf3D7_06_v3-1197245-1197515-1A"
## [25] "Pf3D7_06_v3-1282656-1282930-1A" "Pf3D7_06_v3-176108-176338-1A"
## [27] "Pf3D7_06_v3-416462-416720-1A" "Pf3D7_06_v3-532166-532407-1A"
## [29] "Pf3D7_07_v3-1028330-1028603-1A" "Pf3D7_07_v3-105172-105442-1A"
## [31] "Pf3D7_07_v3-1066661-1066903-1A" "Pf3D7_07_v3-403801-404052-1B"
## [33] "Pf3D7_07_v3-404325-404590-1B" "Pf3D7_07_v3-405517-405773-2"
## [35] "Pf3D7_07_v3-405570-405844-1B" "Pf3D7_07_v3-717260-717493-1A"
## [37] "Pf3D7_08_v3-1313088-1313338-1A" "Pf3D7_08_v3-1314717-1314986-1A"
## [39] "Pf3D7_08_v3-1366575-1366822-2" "Pf3D7_08_v3-1370603-1370853-1B"
## [41] "Pf3D7_08_v3-1375025-1375284-1B" "Pf3D7_08_v3-1375205-1375450-2"
## [43] "Pf3D7_08_v3-1386786-1387035-2" "Pf3D7_08_v3-412801-413062-1A"
## [45] "Pf3D7_08_v3-476232-476475-1A" "Pf3D7_08_v3-550057-550318-2"
## [47] "Pf3D7_08_v3-585703-585949-1A" "Pf3D7_08_v3-585993-586266-1A"
## [49] "Pf3D7_09_v3-1015103-1015350-1A" "Pf3D7_09_v3-164045-164311-1A"
## [51] "Pf3D7_09_v3-270915-271160-1A" "Pf3D7_10_v3-992331-992603-1A"
## [53] "Pf3D7_10_v3-992596-992869-1A" "Pf3D7_11_v3-1006693-1006917-1A"
## [55] "Pf3D7_11_v3-1018781-1019053-1A" "Pf3D7_11_v3-1294284-1294580-1B"
## [57] "Pf3D7_11_v3-1950431-1950680-2" "Pf3D7_11_v3-2001725-2001999-2"
## [59] "Pf3D7_11_v3-408285-408534-1A" "Pf3D7_11_v3-497277-497548-1A"
## [61] "Pf3D7_12_v3-529495-529767-1A" "Pf3D7_12_v3-659881-660127-1A"
## [63] "Pf3D7_12_v3-857050-857323-1A" "Pf3D7_13_v3-1004740-1005002-1A"
## [65] "Pf3D7_13_v3-1041593-1041860-1AB" "Pf3D7_13_v3-1406713-1406975-1A"
## [67] "Pf3D7_13_v3-1465010-1465307-1B" "Pf3D7_13_v3-1465616-1465890-1A"
## [69] "Pf3D7_13_v3-156456-156685-1A" "Pf3D7_13_v3-156713-156986-1A"
## [71] "Pf3D7_13_v3-1725379-1725652-2" "Pf3D7_13_v3-1725464-1725719-1B"
## [73] "Pf3D7_13_v3-1725887-1726123-2" "Pf3D7_13_v3-1876391-1876664-1A"
## [75] "Pf3D7_13_v3-2114829-2115090-1A" "Pf3D7_13_v3-2504481-2504734-1B"
## [77] "Pf3D7_13_v3-2770591-2770863-2" "Pf3D7_13_v3-2770621-2770854-1B"
## [79] "Pf3D7_13_v3-2840447-2840746-2" "Pf3D7_13_v3-2840462-2840736-1B"
## [81] "Pf3D7_13_v3-2841390-2841688-1B2" "Pf3D7_13_v3-2844334-2844629-1B2"
## [83] "Pf3D7_13_v3-748254-748510-1B" "Pf3D7_13_v3-935613-935884-1A"
## [85] "Pf3D7_13_v3-958247-958510-1B" "Pf3D7_14_v3-1038300-1038538-1A"
## [87] "Pf3D7_14_v3-1166107-1166371-1A" "Pf3D7_14_v3-120101-120365-1A"
## [89] "Pf3D7_14_v3-1392837-1393086-1A" "Pf3D7_14_v3-1956056-1956330-1B"
## [91] "Pf3D7_14_v3-2020604-2020849-1A" "Pf3D7_14_v3-2481033-2481276-1B"
## [93] "Pf3D7_14_v3-2695837-2696082-1A" "Pf3D7_14_v3-921176-921432-1A"
## [95] "PvP01_12_v1-1184983-1185208-1AB"
## # A tibble: 273 × 2
## locus length_type
## <chr> <int>
## 1 Pf3D7_01_v3-162867-163115-1A 208
## 2 Pf3D7_01_v3-162867-163115-1A 202
## 3 Pf3D7_01_v3-162867-163115-1A 211
## 4 Pf3D7_01_v3-162867-163115-1A 209
## 5 Pf3D7_01_v3-162867-163115-1A 205
## 6 Pf3D7_01_v3-194742-194973-1B 177
## 7 Pf3D7_01_v3-194742-194973-1B 186
## 8 Pf3D7_01_v3-194742-194973-1B 195
## 9 Pf3D7_01_v3-194742-194973-1B 183
## 10 Pf3D7_01_v3-455794-456054-1A 193
## # ℹ 263 more rows
## [1] "No reads in any samples for these loci, for 1A/1AB"
## # A tibble: 1 × 3
## locus pool n
## <chr> <chr> <dbl>
## 1 PKNH_12_v2-198869-199113-1AB 1AB NA
## [1] "List of samples that do not have >75% loci with >100 reads, in pool 1A"
## # A tibble: 173 × 7
## # Groups: sampleID [173]
## sampleID pool totreads n50 n100 neg norm
## <chr> <chr> <int> <int> <int> <lgl> <dbl>
## 1 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1A 235 0 0 FALSE 0
## 2 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1A 1989 4 0 FALSE 0
## 3 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1A 8057 61 18 FALSE 0.107
## 4 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1A 464 0 0 FALSE 0
## 5 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1A 989 0 0 FALSE 0
## 6 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1A 2786 7 0 FALSE 0
## 7 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1A 4984 28 6 FALSE 0.0357
## 8 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1A 7523 63 16 FALSE 0.0952
## 9 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1A 9277 77 23 FALSE 0.137
## 10 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1A 698 0 0 FALSE 0
## # ℹ 163 more rows
##
## TRUE
## 47
## [1] "Loci without any reads, pool 5"
## # A tibble: 5 × 16
## `locus-pool` Category chr_malaria ampInsert_start ampInsert_end GeneID Gene
## <chr> <chr> <chr> <dbl> <dbl> <chr> <chr>
## 1 Pf3D7_13_v3-2… Diagnos… Pf3D7_13_v3 2841411 2841661 PF3D7… HRP3
## 2 Pf3D7_13_v3-2… Diagnos… Pf3D7_13_v3 2844355 2844599 <NA> <NA>
## 3 PmUG01_12_v1-… Species PmUG01_12_… 1398021 1398213 PMUG0… ldh
## 4 PocGH01_12_v1… Species PocGH01_12… 1106483 1106671 POCGH… ldh
## 5 PvP01_12_v1-1… Species PvP01_12_v1 1185008 1185184 PVP01… ldh
## # ℹ 9 more variables:
## # `Reason_to_include_(if_drug_resistance:_aminoacids)` <chr>,
## # `Amino_acid_range_(*:_partial_coverage_of_that_aminoacid)` <chr>,
## # pool5 <lgl>, amplicon_id <chr>, amplicon_start <dbl>, amplicon_end <dbl>,
## # fwd_primer <chr>, rev_primer <chr>, n <dbl>
## [1] "List of samples that do not have >75% alleles with >100 reads, pool 5"
## # A tibble: 166 × 7
## # Groups: sampleID [166]
## sampleID pool totreads n50 n100 neg norm
## <chr> <chr> <int> <int> <int> <lgl> <dbl>
## 1 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1B 84 0 0 FALSE 0
## 2 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1B 645 2 0 FALSE 0
## 3 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1B 3200 22 10 FALSE 0.213
## 4 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1B 137 0 0 FALSE 0
## 5 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1B 349 0 0 FALSE 0
## 6 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1B 858 2 0 FALSE 0
## 7 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1B 1548 14 3 FALSE 0.0638
## 8 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1B 2037 18 5 FALSE 0.106
## 9 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1B 3287 24 15 FALSE 0.319
## 10 Gambia_Indie-1B_MH_1_AE_2023_03_06_8… 1B 266 0 0 FALSE 0
## # ℹ 156 more rows
## Rows: 31 Columns: 14
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (10): locus-pool, Category, chr_malaria, GeneID, Gene, Reason to include...
## dbl (4): ampInsert_start, ampInsert_end, amplicon_start, amplicon_end
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
bind_tog <- bind_rows(bad_1A, bad_5) %>%
filter(!grepl("Neg", sampleID)) %>%
filter(!grepl("Pos", sampleID))
table(bind_tog$sampleID)
##
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068185300_PR1A5_S298
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068185323_PR1A5_S218
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068185326_PR1A5_S242
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068185343_PR1A5_S264
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068185391_PR1A5_S214
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068185401_PR1A5_S216
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068185567_PR1A5_S229
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068185722_PR1A5_S250
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068185876_PR1A5_S288
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068185891_PR1A5_S276
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068185903_PR1A5_S262
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068185939_PR1A5_S274
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068186019_PR1A5_S228
## 1
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068186025_PR1A5_S286
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068186063_PR1A5_S300
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068186076_PR1A5_S287
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068186110_PR1A5_S240
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068186138_PR1A5_S263
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068186207_PR1A5_S241
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068279974_PR1A5_S306
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068279988_PR1A5_S293
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068279991_PR1A5_S304
## 1
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068279996_PR1A5_S255
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280016_PR1A5_S283
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280025_PR1A5_S284
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280046_PR1A5_S261
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280050_PR1A5_S224
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280052_PR1A5_S248
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280058_PR1A5_S303
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280081_PR1A5_S268
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280088_PR1A5_S285
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280106_PR1A5_S221
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280170_PR1A5_S270
## 1
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280181_PR1A5_S295
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280188_PR1A5_S249
## 1
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280201_PR1A5_S256
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280279_PR1A5_S222
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280282_PR1A5_S236
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280290_PR1A5_S257
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280303_PR1A5_S246
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280304_PR1A5_S282
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280374_PR1A5_S266
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280398_PR1A5_S272
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280432_PR1A5_S260
## 2
## Gambia_Indie-1B_MH_1_AE_2023_03_06_8068280471_PR1A5_S225
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068279954_PR1A5_S391
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068279957_PR1A5_S370
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068279962_PR1A5_S369
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068279967_PR1A5_S380
## 1
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068279976_PR1A5_S356
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068279983_PR1A5_S335
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068279990_PR1A5_S314
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068279999_PR1A5_S403
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280004_PR1A5_S316
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280029_PR1A5_S317
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280043_PR1A5_S333
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280059_PR1A5_S321
## 1
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280060_PR1A5_S373
## 1
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280071_PR1A5_S358
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280080_PR1A5_S357
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280095_PR1A5_S332
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280117_PR1A5_S319
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280118_PR1A5_S382
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280144_PR1A5_S381
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280165_PR1A5_S343
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280195_PR1A5_S334
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280206_PR1A5_S350
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280213_PR1A5_S325
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280215_PR1A5_S384
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280218_PR1A5_S328
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280219_PR1A5_S383
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280224_PR1A5_S389
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280236_PR1A5_S312
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280243_PR1A5_S346
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280250_PR1A5_S401
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280252_PR1A5_S385
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280286_PR1A5_S344
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280296_PR1A5_S387
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280300_PR1A5_S348
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280312_PR1A5_S378
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280323_PR1A5_S386
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280325_PR1A5_S364
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280326_PR1A5_S400
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280411_PR1A5_S371
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280421_PR1A5_S374
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280430_PR1A5_S322
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280506_PR1A5_S399
## 2
## Gambia_Indie-1B_MH_2_AE_2023_03_28_8068280520_PR1A5_S331
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068279968_PR1A5_S449
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068279985_PR1A5_S441
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068279995_PR1A5_S429
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280003_PR1A5_S423
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280006_PR1A5_S434
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280007_PR1A5_S448
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280020_PR1A5_S499
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280045_PR1A5_S463
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280048_PR1A5_S442
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280074_PR1A5_S457
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280083_PR1A5_S415
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280090_PR1A5_S409
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280101_PR1A5_S446
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280104_PR1A5_S484
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280116_PR1A5_S435
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280124_PR1A5_S420
## 1
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280151_PR1A5_S493
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280159_PR1A5_S440
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280162_PR1A5_S410
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280164_PR1A5_S436
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280177_PR1A5_S462
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280184_PR1A5_S491
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280196_PR1A5_S458
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280203_PR1A5_S445
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280207_PR1A5_S468
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280231_PR1A5_S470
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280235_PR1A5_S424
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280239_PR1A5_S406
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280276_PR1A5_S492
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280283_PR1A5_S454
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280288_PR1A5_S456
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280298_PR1A5_S482
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280310_PR1A5_S426
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280315_PR1A5_S466
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280316_PR1A5_S479
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280320_PR1A5_S464
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280334_PR1A5_S467
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280346_PR1A5_S485
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280349_PR1A5_S407
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280351_PR1A5_S425
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280375_PR1A5_S418
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280393_PR1A5_S495
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280394_PR1A5_S431
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280396_PR1A5_S408
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280406_PR1A5_S497
## 1
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280409_PR1A5_S472
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280414_PR1A5_S432
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280429_PR1A5_S413
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280460_PR1A5_S444
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280469_PR1A5_S428
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280481_PR1A5_S476
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280485_PR1A5_S412
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280505_PR1A5_S447
## 2
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280516_PR1A5_S461
## 1
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280519_PR1A5_S460
## 1
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280591_PR1A5_S414
## 1
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280608_PR1A5_S465
## 1
## Gambia_Indie-1B_MH_3_AE_2023_03_30_8068280683_PR1A5_S477
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068279948_PR1A5_S518
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068279953_PR1A5_S516
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068279965_PR1A5_S545
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068279981_PR1A5_S558
## 1
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068279993_PR1A5_S550
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280023_PR1A5_S551
## 1
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280027_PR1A5_S534
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280057_PR1A5_S541
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280126_PR1A5_S503
## 1
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280130_PR1A5_S528
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280134_PR1A5_S539
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280160_PR1A5_S519
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280211_PR1A5_S513
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280220_PR1A5_S530
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280225_PR1A5_S535
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280227_PR1A5_S557
## 1
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280237_PR1A5_S560
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280244_PR1A5_S548
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280292_PR1A5_S559
## 1
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280416_PR1A5_S537
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280419_PR1A5_S549
## 1
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280427_PR1A5_S556
## 1
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280440_PR1A5_S561
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280511_PR1A5_S538
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280512_PR1A5_S544
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280632_PR1A5_S527
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280637_PR1A5_S529
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280659_PR1A5_S536
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280666_PR1A5_S555
## 1
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280680_PR1A5_S552
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280685_PR1A5_S526
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280697_PR1A5_S531
## 2
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280711_PR1A5_S508
## 1
## Gambia_Indie-1B_MH_4_AE_2023_04_05_8068280715_PR1A5_S543
## 2
# samples that need to be re-prepped
re_prep_or_re_seq <- bind_rows(bad_1A_reprep, bad_1A_repool, bad_5_reprep, bad_5_repool)
re_prep_or_re_seq <- re_prep_or_re_seq %>%
filter(!grepl("Neg", sampleID)) %>%
filter(!grepl("control", sampleID)) %>%
filter(!grepl("Control", sampleID))
wider <- re_prep_or_re_seq %>%
select(sampleID, pool, reprep, repool) %>%
pivot_wider(id_cols = sampleID, names_from = pool, values_from = c(reprep, repool))
# replace NAs (which mean that the samples had enough reads in that pool) with 0s
wider[is.na(wider)] <- 0
# now you need to deal with collapsing by sample -- if any need to be reprepped, then all need to be reprepped
re_prep <- wider %>%
filter(reprep_1A == 1 | reprep_1B == 1) %>%
select(sampleID) %>%
mutate(reprep = 1, repool = 0)
re_pool <- wider %>%
anti_join(re_prep) %>%
select(sampleID) %>%
mutate(reprep = 0, repool = 1)
## Joining with `by = join_by(sampleID)`
write.csv(re_prep, "gambia_failedQC_reprep.csv", row.names = FALSE)
write.csv(re_pool, "gambia_failedQC_repool.csv", row.names = FALSE)
## [1] "Sample size= 145"
## [1] "# of entries excluded = 0, Prop. excluded = 0"
## [1] "# of loci after cleanup = 242"
## character(0)
# Use allele_data (sample filtered, but no locus/allele filtered) as moire input
moire_input <- data_filt %>%
select (sampleID, locus, allele) %>%
rename("sample_id" = "sampleID") %>%
distinct()
write.csv(moire_input, "gambia_moire_input.csv", row.names = F)